While recent advances in artificial intelligence have achieved human-level performance in environments like Starcraft and Go, many physical reasoning tasks remain challenging for modern algorithms. To date, few algorithms have been evaluated on physical tasks that involve manipulating objects when movable obstacles are present and when tools must be used to perform the manipulation. To promote research on such tasks, we introduce PushWorld, an environment with simplistic physics that requires manipulation planning with both movable obstacles and tools. We provide a benchmark of more than 200 PushWorld puzzles in PDDL and in an OpenAI Gym environment. We evaluate state-of-the-art classical planning and reinforcement learning algorithms on this benchmark, and we find that these baseline results are below human-level performance. We then provide a new classical planning heuristic that solves the most puzzles among the baselines, and although it is 35 times faster than the best baseline planner, it remains below human-level performance.
翻译:虽然最近人工智能的进步在Starcraft和Go等环境中取得了人类层面的绩效,但许多物理推理任务对现代算法仍然具有挑战性。 到目前为止,在存在移动障碍和必须使用工具进行操纵时,很少有算法被评估到涉及操纵物体的物理任务。为了推动对此类任务的研究,我们引入了普什世界,这是一个简单物理学环境,需要用移动障碍和工具进行操纵规划。我们在PDDL和OpenAI Gym环境中提供了一个200多个推式世界拼图的基准。我们评估了这一基准的最新古典规划和强化学习算法,我们发现这些基线结果低于人类层面的绩效。我们随后提供了一种新的经典规划精华,解决了基线中最棘手的问题,尽管比最好的基线规划员快35倍,但仍低于人类层面的绩效。